MPI runtime error detection with MUST: Advances in deadlock detection

Hilbrich, Tobias; Protze, Joachim; Schulz, Martin; Supinski, Bronis de; Mueller, Matthias

doi:10.1109/sc.2012.79

Cited by 43 publications

(26 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike model checkers (such as TASS [22]), our approach scales to any number of processes, running in constant time. No runtime verification of the software is necessary as in ISP [17], DAMPI [24] or MUST [10]. These tools do not require protocols and typically require less program annotations, but the runtime verifiers require a good test suite which is much harder to write than a protocol.…”

Section: Resultsmentioning

confidence: 99%

Deductive Verification of Parallel Programs Using Why3

Santos

Martins

Vasconcelos

2015

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

The Message Passing Interface specification (MPI) defines a portable message-passing API used to program parallel computers. MPI programs manifest a number of challenges on what concerns correctness: sent and expected values in communications may not match, resulting in incorrect computations possibly leading to crashes; and programs may deadlock resulting in wasted resources. Existing tools are not completely satisfactory: model-checking does not scale with the number of processes; testing techniques wastes resources and are highly dependent on the quality of the test set. As an alternative, we present a prototype for a type-based approach to programming and verifying MPI like programs against protocols. Protocols are written in a dependent type language designed so as to capture the most common primitives in MPI, incorporating, in addition, a form of primitive recursion and collective choice. Protocols are then translated into Why3, a deductive software verification tool. Source code, in turn, is written in WhyML, the language of the Why3 platform, and checked against the protocol. Programs that pass verification are guaranteed to be communication safe and free from deadlocks. We verified several parallel programs from textbooks using our approach, and report on the outcome.Comment: In Proceedings ICE 2015, arXiv:1508.0459

show abstract

Section: Resultsmentioning

confidence: 99%

Deductive Verification of Parallel Programs Using Why3

Santos

Martins

Vasconcelos

2015

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…Dynamic analyses are widely used for analyzing MPI programs. Debugging or testing tools [1,36,50,51,60,71,87] have better feasibility and scalability but depend on specific inputs and running schedules. Dynamic verification techniques, e.g., ISP [83] and DAMPI [84], run MPI programs multiple times to cover the schedules under the same inputs.…”

Section: Related Workmentioning

confidence: 99%

Combining symbolic execution and model checking to verify MPI programs

2018

Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings

View full text Add to dashboard Cite

Message passing is the standard paradigm of programming in highperformance computing. However, verifying Message Passing Interface (MPI) programs is challenging, due to the complex program features (such as non-determinism and non-blocking operations). In this work, we present MPI symbolic verifier (MPI-SV), the first symbolic execution based tool for automatically verifying MPI programs with non-blocking operations. MPI-SV combines symbolic execution and model checking in a synergistic way to tackle the challenges in MPI program verification. The synergy improves the scalability and enlarges the scope of verifiable properties. We have implemented MPI-SV 1 and evaluated it with 111 real-world MPI verification tasks. The pure symbolic execution-based technique successfully verifies 61 out of the 111 tasks (55%) within one hour, while in comparison, MPI-SV verifies 100 tasks (90%). On average, compared with pure symbolic execution, MPI-SV achieves 19x speedups on verifying the satisfaction of the critical property and 5x speedups on finding violations. CCS CONCEPTS• Software and its engineering → Software verification and validation;

show abstract

“…Knapp introduced the WFGs [40] to model concurrency constraints directly between tasks. As discussed earlier, variations of WFGs are used in the state-of-the-art on deadlock detection for distributed message passing and (static membership) barriers [34,37].…”

Section: Task-event Graphsmentioning

confidence: 99%

Dynamic Deadlock Verification for General Barrier Synchronisation

Cogumbreiro

Martins

et al. 2018

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

We present Armus, a verification tool for dynamically detecting or avoiding barrier deadlocks. The core design of Armus is based on phasers, a generalisation of barriers that supports split-phase synchronisation, dynamic membership, and optional-waits. This allows Armus to handle the key barrier synchronisation patterns found in modern languages and libraries. We implement Armus for X10 and Java, giving the first sound and complete barrier deadlock verification tools in these settings. Armus introduces a novel event-based graph model of barrier concurrency constraints that distinguishes task-event and event-task dependencies. Decoupling these two kinds of dependencies facilitates the verification of distributed barriers with dynamic membership, a challenging feature of X10. Further, our base graph representation can be dynamically switched between a task-to-task model, Wait-for Graph (WFG), and an event-to-event model, State Graph (SG), to improve the scalability of the analysis. Formally, we show that the verification is sound and complete with respect to the occurrence of deadlock in our core phaser language, and that switching graph representations preserves the soundness and completeness properties. These results are machine checked with the Coq proof assistant. Practically, we evaluate the runtime overhead of our implementations using three benchmark suites in local and distributed scenarios. Regarding deadlock detection, distributed scenarios show negligible overheads and local scenarios show overheads below 1.15×. Deadlock avoidance is more demanding, and highlights the potential gains from dynamic graph selection. In one benchmark scenario, the runtime overheads vary from 1.8× for dynamic selection, 2.6× for SG-static selection, and 5.9× for WFG-static selection.

show abstract

MPI runtime error detection with MUST: Advances in deadlock detection

Cited by 43 publications

References 11 publications

Deductive Verification of Parallel Programs Using Why3

Deductive Verification of Parallel Programs Using Why3

Combining symbolic execution and model checking to verify MPI programs

Dynamic Deadlock Verification for General Barrier Synchronisation

Contact Info

Product

Resources

About